作者: Giuseppe Attardi , Maria Simi , E. M. Vecchi , A. Fuschetto , F. Tamberi
DOI:
关键词:
摘要: The paper reports experiments with several strategies of tagger combination, using two well known taggers, TreeTagger and Hunpos. most successful experiment,which achieved the best score in Evalita 2009 Open Task, is a hybrid solution combining an easiest first iterative strategy hand-written arbitration rules quality lexicon. system used Closed Task uses similar combination variants Hunpos, together correction/guessing rules.